This repository offers a ROS Node with GPT4V model.
catkin build gpt4v_vqa
roslaunch gpt4v_vqa vqa.launch api_key:=<YOUR_API_KEY> VQA_INPUT_IMAGE:=<IMAGE TOPIC>
And from other terminal
$ rosrun gpt4v_vqa vqa_interpreter.py
This node is a ROS wrapper for GPT4V model. Its behavior is similar to VQA node. But there is a difference that this node does not support continuous inference. This node use API only when action server is called.
-
~image
([sensor_msgs/Image])The image used for VQA as default image.
-
~inference_server
([jsk_recognition_msgs/VQATaskAction])The action server for VQA.